Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 130524
    Prev
    Next
    INDEX
    Explanations

    code dependencies

    np_max-act · gemini-2.0-flash

    This neuron activates on XML/HTML‐style tags and their angle‐bracketed elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _poly
    -0.07
     Carlson
    -0.06
     talent
    -0.06
     언어
    -0.06
    linky
    -0.06
    [email
    -0.06
     surrogate
    -0.06
    baseline
    -0.06
     Erg
    -0.06
    _EMAIL
    -0.06
    POSITIVE LOGITS
     осуществ
    0.06
    ustr
    0.06
    мін
    0.06
     unlikely
    0.06
     nova
    0.06
    식
    0.06
    эф
    0.06
    имв
    0.06
     ventured
    0.06
    reasonable
    0.06
    Activations Density 0.021%

    No Known Activations